© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1723
    Prev
    Next
    INDEX
    Explanations

    at some point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     보기
    -0.10
    ç»ĻäºĨæĪij
    -0.10
    å¸ĥæľĹ
    -0.10
     недо
    -0.09
    ä¸į容æĺĵ
    -0.09
     пÑĢежде
    -0.09
     Ñĥни
    -0.09
    è¿Ļ件
    -0.09
    .hasNext
    -0.09
    çŃĽ
    -0.09
    POSITIVE LOGITS
    æĩĤäºĭ
    0.08
    ä¸įåIJĮç¨ĭ度
    0.08
     ballo
    0.08
    pd
    0.08
    anche
    0.08
     Commonwealth
    0.08
    æŶåĢĻ
    0.08
    æĿijéķĩ
    0.07
    ãĤ£
    0.07
    åĨ³
    0.07
    Activations Density 0.031%

    No Known Activations